A multi-centre, prospective, double-blinded, pilot study evaluating artificial intelligence driven automatic detection of proximal deep vein thrombosis (DVT).

Our long term vision is to revolutionize the cumbersome diagnostic pathway for DVT.

We aim to use ground-breaking artificial intelligence (AI) software to eliminate the need for highly trained, resource limited, ultrasound specialists. It is likely that healthcare systems will be impacted worldwide.

AutoDVT (the AI software) is designed to support the diagnosis of DVT at any medical facility (hospital/community) by any clinician.

This will markedly reduce waiting times; eliminate unnecessary high-risk anticoagulation therapy; minimise scans performed by radio-graphers/logists; improve patient safety and satisfaction; and reduce healthcare costs. The funding requested will support the first step in the clinical evaluation of AutoDVT.

Our aim is to establish the diagnostic sensitivity of AutoDVT when used by radiology non-specialists. This is vital for progressing with regulatory requirements and securing AutoDVT's place in the healthcare market.

The next step is to conduct a large, multi-centre, randomised controlled trial to confirm the efficacy and safety of AutoDVT (n = 3,500; estimated cost £2.5M). This will include full health economic analysis.

Assuming AutoDVT is efficacious and safe, we will position it’s use as a point-of-care device in ambulatory care and establish a novel diagnostic pathway for DVT, improving care to many hundreds of thousands annually.